CN113040787B - Method, device, processor and storage medium for extracting and processing MMN signal characteristics for evaluating sensory gating function - Google Patents
Method, device, processor and storage medium for extracting and processing MMN signal characteristics for evaluating sensory gating function Download PDFInfo
- Publication number
- CN113040787B CN113040787B CN202110448301.0A CN202110448301A CN113040787B CN 113040787 B CN113040787 B CN 113040787B CN 202110448301 A CN202110448301 A CN 202110448301A CN 113040787 B CN113040787 B CN 113040787B
- Authority
- CN
- China
- Prior art keywords
- mmn
- extracting
- sensory gating
- processor
- amplitude
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000009151 sensory gating Effects 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012545 processing Methods 0.000 title claims abstract description 25
- 230000006870 function Effects 0.000 claims abstract description 48
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 210000004556 brain Anatomy 0.000 claims abstract description 13
- 238000010801 machine learning Methods 0.000 claims abstract description 9
- 238000007619 statistical method Methods 0.000 claims abstract description 5
- 230000000638 stimulation Effects 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 17
- 208000020925 Bipolar disease Diseases 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000002790 cross-validation Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 230000000698 schizophrenic effect Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012880 independent component analysis Methods 0.000 claims description 4
- 238000000556 factor analysis Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 208000020016 psychiatric disease Diseases 0.000 abstract description 5
- 201000000980 schizophrenia Diseases 0.000 description 14
- 230000004044 response Effects 0.000 description 5
- 208000019022 Mood disease Diseases 0.000 description 4
- 208000030459 obsessive-compulsive personality disease Diseases 0.000 description 4
- 208000007656 osteochondritis dissecans Diseases 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 3
- 208000024891 symptom Diseases 0.000 description 3
- 230000001225 therapeutic effect Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000004064 dysfunction Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 208000017194 Affective disease Diseases 0.000 description 1
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 208000028017 Psychotic disease Diseases 0.000 description 1
- 238000010171 animal model Methods 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000000090 biomarker Substances 0.000 description 1
- 208000028683 bipolar I disease Diseases 0.000 description 1
- 208000025307 bipolar depression Diseases 0.000 description 1
- 208000030963 borderline personality disease Diseases 0.000 description 1
- 206010006475 bronchopulmonary dysplasia Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001543 one-way ANOVA Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008506 pathogenesis Effects 0.000 description 1
- 230000011514 reflex Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 210000004761 scalp Anatomy 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000009528 severe injury Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
- A61B5/4088—Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
- A61B5/7207—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Psychiatry (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Neurology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Developmental Disabilities (AREA)
- Child & Adolescent Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Educational Technology (AREA)
- Neurosurgery (AREA)
- Social Psychology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention relates to a method for extracting and processing MMN signal characteristics for evaluating a sensory gating function, which comprises the following steps: collecting brain wave data; MMN pretreatment is carried out; performing numerical statistical analysis on the amplitude and the latency of the MMN by adopting a characteristic analysis method; performing machine learning classification on the time-related potential to obtain a classification result; comparing the event related potential waveforms before and after treatment of the patient with the average level of 3 groups to obtain an analysis result; MMN amplitude and latency were extracted. The invention also relates to a device, a processor and a storage medium thereof for extracting and processing MMN signal characteristics for evaluating the sensory gating function. The method, the device, the processor and the computer readable storage medium thereof for extracting and processing the MMN signal characteristics aiming at evaluating the sensory gating function are adopted to compare the waveform and the amplitude of the tested MMN curve with those of the standard curve so as to evaluate the sensory gating function; and using an MMN sensory gating system to predict mental diseases through machine learning, and evaluating the treatment effect of patients.
Description
Technical Field
The invention relates to the field of brain electric physiological indexes for evaluating gating functions, in particular to a method, a device, a processor and a computer readable storage medium for extracting and processing MMN signal characteristics for evaluating sensory gating functions.
Background
Sensory gating dysfunction is a prominent internal phenotypic trait in schizophrenic patients, and the shock reflex test (PPI), which reflects sensory gating function in animals, is often used as a characteristic indicator for establishing an animal model of schizophrenia. Develop accurate biological index evaluating human sensory gating function, and has important significance for clinically distinguishing schizophrenia and other mental diseases.
Event-related potential MMN (MISMATCH NEGATIVITY, MMN, mismatching negative wave) is a differential wave of event-related potential that can be induced even if standard and deviation stimuli (typically 90%:10% and 80%: 20%) occur in a proportion without special attention. This differential wave reflects to some extent the brain's ability to distinguish between targets and background, i.e. sensory gating functions. The good sensory gating function can filter background information and pay attention to the target, otherwise, irrelevant important background interference cannot be filtered, a patient is difficult to grasp the target, and redundant background information interferes with thinking of the patient, so that mental symptoms such as thinking confusion and the like appear.
At present, clinical researches show that the MMN amplitude is related to the schizophrenia, and compared with healthy people, the MMN amplitude of the schizophrenia patient is reduced, but no normal value of the MMN amplitude exists at present, so that the MMN amplitude cannot be used as an index for evaluating the sensory gating function.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a method, a device, a processor and a computer readable storage medium thereof for extracting MMN signal characteristics aiming at evaluation of a sensory gating function, wherein the method, the device, the processor and the computer readable storage medium are accurate in data, simple and convenient to operate and wide in application range.
To achieve the above object, a method, an apparatus, a processor, and a computer-readable storage medium thereof for extracting and processing MMN signal features for evaluating a sensory gating function according to the present invention are as follows:
The method for extracting and processing MMN signal characteristics for evaluating the sensory gating function is mainly characterized by comprising the following steps of:
(1) Collecting brain wave data;
(2) MMN pretreatment is carried out;
(3) Performing numerical statistical analysis on the amplitude and the latency of the MMN by adopting a characteristic analysis method;
(4) Performing machine learning classification on the time-related potential to obtain a classification result;
(5) Comparing the event related potential waveforms before and after treatment of the patient with the average level of 3 groups to obtain an analysis result;
(6) MMN amplitude and latency were extracted.
Preferably, the step (2) specifically includes the following steps:
(2.1) filtering by a band-pass filter of 0.1-30 Hz;
(2.2) carrying out 50Hz notch processing on a power frequency band;
(2.3) performing channel positioning;
(2.4) performing independent component analysis to remove electro-oculogram components and changing a reference electrode;
(2.5) segmenting an electroencephalogram signal by arranging bin files, and performing baseline calibration;
(2.6) removing the larger artifact portion data;
(2.7) respectively carrying out superposition and average on the standard stimulus and the deviation stimulus to obtain two event related potentials, and subtracting to obtain a difference wave;
(2.8) extracting the peak value and latency of MMN in the difference wave to obtain the amplitude and waveform.
Preferably, the step (2.6) specifically includes the following steps:
The large artifact segments are removed based on the judgment that the single threshold exceeds + -100 microvolts and the peak fluctuation exceeds + -100 microvolts within 200 ms.
Preferably, the step (3) specifically includes the following steps:
And performing multi-sample single-factor analysis of variance test, adding age to perform covariance, and performing correlation analysis on the amplitude of the MMN to obtain the amplitude sensory gating function threshold.
Preferably, the method further comprises a step of predicting test set data, and specifically comprises the following steps:
dividing according to the proportion of the tested types of the total sample, training a model by using a ten-fold cross validation method, predicting the rest data, comparing the result with a label, and evaluating the accuracy.
Preferably, the step (1) specifically includes the following steps:
And (3) using an electroencephalogram acquisition system to acquire electroencephalogram data, guiding a tested person to see a silent video, and simultaneously playing standard stimulation and deviation stimulation, wherein the occurrence probability of the standard stimulation is 90%, the occurrence probability of the deviation stimulation is 10%, and the deviation stimulation only occurs after at least 6 standard stimulation.
The device for extracting and processing MMN signal characteristics for evaluating the sensory gating function is mainly characterized by comprising the following components:
A processor configured to execute computer-executable instructions;
And a memory storing one or more computer executable instructions which, when executed by the processor, implement the steps of the method for extracting MMN signal features for evaluation of sensory gating functions described above.
The processor for extracting and processing the MMN signal characteristics of the evaluation sensory gating function is mainly characterized in that the processor is configured to execute computer executable instructions, and the steps of the method for extracting and processing the MMN signal characteristics of the evaluation sensory gating function are realized when the computer executable instructions are executed by the processor.
The computer readable storage medium is characterized in that the computer program is stored thereon, and the computer program can be executed by a processor to implement the steps of the method for extracting and processing MMN signal characteristics for evaluating the sensory gating function.
The method, the device, the processor and the computer readable storage medium thereof for extracting and processing the MMN signal characteristics aiming at evaluating the sensory gating function are adopted to compare the waveform and the amplitude of the tested MMN curve with those of the standard curve so as to evaluate the sensory gating function; and using MMN sensory gating system to predict mental diseases such as schizophrenia, bipolar disorder, depression, etc. by machine learning; the present invention uses curve comparison of MMN before and after treatment to evaluate the therapeutic efficacy of patients.
Drawings
FIG. 1 is a flow chart of a method of the present invention for extracting MMN signal features for evaluation of sensory gating functions.
FIG. 2 is a flowchart of MMN preprocessing for the method of extracting MMN signal features for evaluation of sensory gating functions according to the present invention.
Fig. 3 is a schematic representation of the level of MMN latency significantly lower in schizophrenic patients (SCZ) than in bipolar disorder patients (BPD) and Healthy Controls (HC).
Fig. 4 is a graph of age-based covariance analysis showing that the MMN amplitude of SCZ and BPD patients is significantly lower than HC group levels according to the invention.
Fig. 5 is a graph showing the horizontal approach of waveforms to healthy control group after treatment of Subjects (SCZ) according to the present invention.
FIG. 6 is a graph showing the horizontal draw of waveforms to a healthy control group after treatment with a subject (OCD) according to the present invention.
Detailed Description
In order to more clearly describe the technical contents of the present invention, a further description will be made below in connection with specific embodiments.
The method for extracting and processing the MMN signal characteristics aiming at evaluating the sensory gating function comprises the following steps:
(1) Collecting brain wave data;
(2) MMN pretreatment is carried out;
(2.1) filtering by a band-pass filter of 0.1-30 Hz;
(2.2) carrying out 50Hz notch processing on a power frequency band;
(2.3) performing channel positioning;
(2.4) performing independent component analysis to remove electro-oculogram components and changing a reference electrode;
(2.5) segmenting an electroencephalogram signal by arranging bin files, and performing baseline calibration;
(2.6) removing the larger artifact portion data;
Removing the segment with large artifacts according to the judging condition that the single threshold exceeds +/-100 microvolts and the peak fluctuation exceeds +/-100 microvolts within 200 ms;
(2.7) respectively carrying out superposition and average on the standard stimulus and the deviation stimulus to obtain two event related potentials, and subtracting to obtain a difference wave;
(2.8) extracting the peak value and the latency of the MMN in the difference wave to obtain an amplitude and a waveform;
(3) Performing numerical statistical analysis on the amplitude and the latency of the MMN by adopting a characteristic analysis method;
Performing multi-sample single-factor analysis of variance test, adding age to perform covariance, and performing correlation analysis on the amplitude of MMN to obtain a sense gating function threshold of the amplitude;
(4) Performing machine learning classification on the time-related potential to obtain a classification result;
(5) Comparing the event related potential waveforms before and after treatment of the patient with the average level of 3 groups to obtain an analysis result;
(6) MMN amplitude and latency were extracted.
As a preferred embodiment of the invention, the method further comprises the step of predicting test set data, and specifically comprises the following steps:
dividing according to the proportion of the tested types of the total sample, training a model by using a ten-fold cross validation method, predicting the rest data, comparing the result with a label, and evaluating the accuracy.
As a preferred embodiment of the present invention, the step (1) specifically includes the steps of:
And (3) using an electroencephalogram acquisition system to acquire electroencephalogram data, guiding a tested person to see a silent video, and simultaneously playing standard stimulation and deviation stimulation, wherein the occurrence probability of the standard stimulation is 90%, the occurrence probability of the deviation stimulation is 10%, and the deviation stimulation only occurs after at least 6 standard stimulation.
The device for extracting and processing MMN signal characteristics for evaluating the sensory gating function comprises:
A processor configured to execute computer-executable instructions;
And a memory storing one or more computer executable instructions which, when executed by the processor, implement the steps of the method for extracting MMN signal features for evaluation of sensory gating functions described above.
The processor of the MMN signal feature extraction processing for evaluation of sensory gating functions of the present invention is configured to execute computer-executable instructions that, when executed by the processor, implement the steps of the method for performing the extraction processing for MMN signal features for evaluation of sensory gating functions described above.
The computer readable storage medium of the present invention has stored thereon a computer program executable by a processor to perform the steps of the above-described method of extracting MMN signal features for evaluation of sensory gating functions.
In the specific embodiment of the invention, in order to develop accurate biological indexes for evaluating sensory gating functions, the invention uses the same set of equipment to acquire the brain electrophysiological data of 676 Chinese people, wherein 208 cases of schizophrenic patients, 144 cases of bipolar disorder patients and 324 healthy controls are adopted. Performing amplitude and waveform characteristic analysis on MMN data by adopting a characteristic analysis method; then, performing machine learning classification by using the amplitude and the latency of the MMN to obtain a classification result; finally, aiming at the tested further analysis of the follow-up data before and after treatment in 12 persons, an MMN chart of each person is drawn, and specific comparison analysis is carried out to obtain an analysis result, as shown in figure 1.
The scientific principle is as follows:
Schizophrenia and affective disorders (including bipolar disorder and depression) are complex, severe mental diseases, the pathogenesis of which is not yet clear, and no objective diagnostic index is provided, which brings difficulty in diagnosis and treatment. Several studies have found that sensory gating dysfunction is an internal phenotype of schizophrenia, with an intrinsic, characteristic significance. Are likely biomarkers that distinguish between schizophrenia and affective disorders.
MN is the electrical activity that can reflect the brain by recording scalp electroencephalogram; recording brain electricity while adding some stimulus can reflect the brain's immediate response to the stimulus. The event-related potential can be obtained by repeatedly superimposing the brain electrical activity responses of the same event stimulus through the marking of the related stimulus. Thus, event-related potentials reflect the brain electrical activity that is being tested after receiving the stimulus. MMN is an event-related potential, in which a small number (not more than 30% in proportion) of deviation stimulus is randomly added to standard stimulus repeated a plurality of times, and the event-related potential of the standard stimulus is subtracted from the event-related potential obtained by the deviation stimulus to obtain MMN. There are now two main mechanisms for MMN, one is the sensory memory hypothesis and the other is the adaptation hypothesis. The memory hypothesis suggests that standard stimuli leave traces in memory, while biased stimuli have properties inconsistent with standard stimuli, which induce MMN. From this point of view, MMN is considered an indicator of error detection, whose magnitude may reflect how much the current stimulus is different from the previous stimulus. Adaptation hypothesis suggests that brain neurons adapt to repeated stimulation, and when repeated times are high, the response to the stimulation is weakened; in contrast, the proportion of the deviation stimulus is smaller, so that the adaptability of the neuron to the deviation stimulus is not as strong as that of the standard stimulus, and the response of the neuron to the deviation stimulus is more obvious; therefore, the event-related potential of the two is subtracted to obtain a remarkable new event-related potential MMN.
MMN is associated with pre-attention auditory processing, has been extensively studied in schizophrenia, and it is consistently believed that the MMN amplitude is reduced in schizophrenic patients (compared to healthy controls). However, the waveform and amplitude of MMN are not currently thresholded for healthy people, schizophrenia, affective disorders. Therefore, the patent develops the marked values of the MMN waveforms and the amplitudes of the response feeling gating of different types of people through large samples.
The specific implementation mode of the invention is as follows:
(1) Data acquisition and pretreatment:
An ANT Neuro 64-lead electroencephalogram acquisition system is used for acquiring electroencephalogram data, and the sampling frequency is 1000Hz. The experimental paradigm adopts oddball paradigms to guide the tested to pay attention to see a section of silent cartoon video, simultaneously wears an in-ear earphone, and plays two pure-tone stimuli, namely standard stimulus and deviation stimulus (the duration is 50ms and 100ms respectively), wherein the occurrence probability of the standard stimulus is 90%, the occurrence probability of the deviation stimulus is 10%, the total number of the 900 trials is 900, the recording takes about 9 minutes, and the deviation stimulus only occurs after at least 6 standard stimuli. In the data preprocessing, the invention firstly uses a 0.1-30Hz band-pass filter to carry out filtering, and also carries out 50Hz notch processing aiming at a power frequency band with care, then uses standard-10-5-cap385.Elp in EEGLAB to carry out channel positioning, then carries out independent component analysis to remove electro-oculogram components, changes a reference electrode, creates an event list file and arranges a bin file to segment an electroencephalogram signal, carries out baseline calibration, uses a single threshold value to exceed +/-100 microvolts and a peak value fluctuation within 200ms to exceed +/-100 microvolts to remove segments with large artifacts, and respectively carries out superposition average on standard stimulation and deviation stimulation to obtain two event related potentials, and the two event related potentials are subtracted to obtain a differential wave. In the differential wave, the peak value and the latency of MMN are extracted using the peak value and latency extraction method in ERPLAB as a window from 150ms to 280ms after stimulation, and the amplitude and waveform are obtained as shown in fig. 2.
(2) MMN numerical statistical analysis:
After the characteristics are obtained, the invention performs One-Way ANOVA test of multiple samples, adds age to perform covariance, and also performs correlation analysis on the amplitude of MMN, so that the obtained amplitude sensory gating function threshold can find that the MMN has obvious difference among three groups, as shown in figures 3 and 4. And for the first time, the waveform (duplex wave) of MMN is an important index of the severity of sensory gating impairment, and both the waveform and the amplitude have important evaluation effects on the sensory gating function. The pattern of the schizophrenic patient group in the MMN window is found to be small in amplitude, obvious duplex waves are generated, and the obvious duplex waves are not generated in BPD and HC, so that the severe damage of the schizophrenic sensory gating function is prompted.
(3) Predictive role of MMN sensory gating system on disease:
The invention also establishes an analysis model of feature extraction and machine learning, uses methods such as KNN, tree, naive Bayes, support vector machine and the like, and adopts a sense-gating evaluation system of the MMN established by the naive Bayes model to predict that the accuracy of predicting two groups of patients with schizophrenia and healthy control groups is 73.55%; the prediction accuracy rate of two groups of bipolar affective disorder and healthy control group is 70.47%; the accuracy of distinguishing schizophrenia from other psychoses (i.e. patients with bipolar disorder, depression, anxiety, etc.) by using the MMN sensory gating evaluation system established by the KNN model is 75.60 percent, as shown in the following table.
(4) Prediction of therapeutic efficacy by MMN sensory gating system: the invention collects 12 patients (including 3 SCZ and 3 BPDs, 1 BPD with OCD,3 OCDs, 2 MDDs). MMN data before and after treatment, and a comparison analysis of amplitude and waveform combination is used to find that the MMN curve of the patient with significantly improved symptoms tends to the healthy control group curve, as shown in fig. 5 for SCZ patients and fig. 6 for OCD patients.
In addition, after the corresponding MMN peak value and the latency period are obtained, the invention also uses a support vector machine to carry out model training and forecast test set data. According to the invention, a ten-fold cross-validation method is used, the total samples are divided into 10 groups according to the tested type proportion of the total samples, each ten-fold cross-validation method is that 9 groups of data in the total samples are subjected to model training, then the rest 1 groups of data are predicted, the result is compared with the label, and the accuracy is evaluated. In order to reduce the influence caused by the randomness of the group, the invention also carries out ten-fold cross validation on the total samples in a disordered order, and the invention uses a 10-time ten-fold cross validation method to record the division of the final prediction result with the same label by the total number of samples as the accuracy.
For the data of follow-up patients, the invention sequentially draws difference wave curves of average levels of the patient before and after treatment and the patient with schizophrenia, the patient with bipolar disorder and the healthy control, takes 3 curves obtained by a large sample as a reference, explores the change condition of the curves of the patient before and after treatment, and finds that the curves of the patient with improved symptoms tend to be close to the average level of the healthy control group.
The specific implementation manner of this embodiment may be referred to the related description in the foregoing embodiment, which is not repeated herein.
It is to be understood that the same or similar parts in the above embodiments may be referred to each other, and that in some embodiments, the same or similar parts in other embodiments may be referred to.
It should be noted that in the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present invention, unless otherwise indicated, the meaning of "plurality" means at least two.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or part of the steps carried out in the method of the above embodiments may be implemented by a program to instruct related hardware, and the corresponding program may be stored in a computer readable storage medium, where the program when executed includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented as software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The method, the device, the processor and the computer readable storage medium thereof for extracting and processing the MMN signal characteristics aiming at evaluating the sensory gating function are adopted to compare the waveform and the amplitude of the tested MMN curve with those of the standard curve so as to evaluate the sensory gating function; and using MMN sensory gating system to predict mental diseases such as schizophrenia, bipolar disorder, depression, etc. by machine learning; the present invention uses curve comparison of MMN before and after treatment to evaluate the therapeutic efficacy of patients.
In this specification, the invention has been described with reference to specific embodiments thereof. It will be apparent that various modifications and variations can be made without departing from the spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.
Claims (7)
1. A method for extracting MMN signal features for evaluating sensory gating functions, the method comprising the steps of:
(1) Collecting brain wave data;
(2) MMN pretreatment is carried out;
(3) Performing numerical statistical analysis on the amplitude and the latency of the MMN by adopting a characteristic analysis method;
(4) Performing machine learning classification on the time-related potential to obtain a classification result;
(5) Comparing the event related potential waveforms before and after treatment of the patient with the average level of 3 groups to obtain an analysis result;
(6) Extracting MMN amplitude and latency;
The step (2) specifically comprises the following steps:
(2.1) filtering by a band-pass filter of 0.1-30 Hz;
(2.2) carrying out 50Hz notch processing on a power frequency band;
(2.3) performing channel positioning;
(2.4) performing independent component analysis to remove electro-oculogram components and changing a reference electrode;
(2.5) segmenting an electroencephalogram signal by arranging bin files, and performing baseline calibration;
(2.6) removing the larger artifact portion data;
(2.7) respectively carrying out superposition and average on the standard stimulus and the deviation stimulus to obtain two event related potentials, and subtracting to obtain a difference wave;
(2.8) extracting the peak value and the latency of the MMN in the difference wave to obtain an amplitude and a waveform;
The step (3) specifically comprises the following steps:
Performing multi-sample single-factor analysis of variance test, adding age to perform covariance, and performing correlation analysis on the amplitude of MMN to obtain a sense gating function threshold of the amplitude;
The average levels of 3 groups in step (5) include average levels before and after treatment with schizophrenic patients, bipolar disorder patients and healthy controls, respectively.
2. The method of claim 1, wherein the step (2.6) specifically comprises the steps of:
The large artifact segments are removed based on the judgment that the single threshold exceeds + -100 microvolts and the peak fluctuation exceeds + -100 microvolts within 200 ms.
3. The method for extracting MMN signal features for evaluation of sensory gating function according to claim 1, further comprising a step of predicting test set data, specifically comprising the steps of:
dividing according to the proportion of the tested types of the total sample, training a model by using a ten-fold cross validation method, predicting the rest data, comparing the result with a label, and evaluating the accuracy.
4. The method for extracting MMN signal features for evaluating sensory gating function according to claim 1, wherein step (1) specifically comprises the steps of:
And (3) using an electroencephalogram acquisition system to acquire electroencephalogram data, guiding a tested person to see a silent video, and simultaneously playing standard stimulation and deviation stimulation, wherein the occurrence probability of the standard stimulation is 90%, the occurrence probability of the deviation stimulation is 10%, and the deviation stimulation only occurs after at least 6 standard stimulation.
5. An apparatus for processing MMN signal feature extraction for evaluation of sensory gating functions, said apparatus comprising:
A processor configured to execute computer-executable instructions;
A memory storing one or more computer-executable instructions which, when executed by the processor, perform the steps of the method of any one of claims 1 to 4 for extracting MMN signal features for evaluation of sensory gating functions.
6. A processor for performing an MMN signal feature extraction process for evaluating sensory gating functionality, characterized in that the processor is configured to execute computer-executable instructions that, when executed by the processor, implement the steps of the method of performing an extraction process for MMN signal features for evaluating sensory gating functionality as claimed in any one of claims 1 to 4.
7. A computer-readable storage medium, having stored thereon a computer program executable by a processor to perform the steps of the method of any one of claims 1 to 4 for extracting MMN signal features for evaluation of sensory gating functions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110448301.0A CN113040787B (en) | 2021-04-25 | 2021-04-25 | Method, device, processor and storage medium for extracting and processing MMN signal characteristics for evaluating sensory gating function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110448301.0A CN113040787B (en) | 2021-04-25 | 2021-04-25 | Method, device, processor and storage medium for extracting and processing MMN signal characteristics for evaluating sensory gating function |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113040787A CN113040787A (en) | 2021-06-29 |
| CN113040787B true CN113040787B (en) | 2024-06-14 |
Family
ID=76520444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110448301.0A Active CN113040787B (en) | 2021-04-25 | 2021-04-25 | Method, device, processor and storage medium for extracting and processing MMN signal characteristics for evaluating sensory gating function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113040787B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118277769B (en) * | 2024-05-29 | 2024-08-16 | 首都医科大学附属北京安定医院 | Perceptual spatial pre-separation pulse suppression data processing method, system and computer readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512500A (en) * | 2015-12-30 | 2016-04-20 | 广州市润杰医疗器械有限公司 | Method for rapidly screening characteristic of schizophrenia and evaluating therapeutic effect |
| CN110063732A (en) * | 2019-04-15 | 2019-07-30 | 北京航空航天大学 | For schizophrenia early detection and Risk Forecast System |
| CN111248907A (en) * | 2020-01-17 | 2020-06-09 | 上海市精神卫生中心（上海市心理咨询培训中心） | Risk prediction method based on electroencephalogram signal characteristics of mental disease clinical high-risk group |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4417592A (en) * | 1981-05-11 | 1983-11-29 | Roy John E | Digital electroencephalographic instrument and method |
| GB0614458D0 (en) * | 2006-07-20 | 2006-08-30 | Clare Jon | Computerised hypnosis therapy device and method |
| CN102946797B (en) * | 2009-08-14 | 2016-12-07 | D·伯顿 | Anesthesia and depth of consciousness monitor system |
| CA2801251C (en) * | 2010-06-22 | 2023-03-28 | National Research Council Of Canada | Cognitive function assessment in a patient |
| US10357175B2 (en) * | 2012-03-12 | 2019-07-23 | Centre Hospitalier Universitaire Vaudois(C.H.U.V.) | Method for predicting awakening in a comatose patient and computer-implemented method thereof |
| JP2016501056A (en) * | 2012-11-10 | 2016-01-18 | ザ レジェンツ オブ ザ ユニヴァーシティー オブ カリフォルニア | System and method for evaluation of neuropathology |
| EP2789293A1 (en) * | 2013-04-12 | 2014-10-15 | Commissariat à l'Énergie Atomique et aux Énergies Alternatives | Methods to monitor consciousness |
| WO2016011189A1 (en) * | 2014-07-15 | 2016-01-21 | The Regents Of The University Of California | Frequency-multiplexed speech-sound stimuli for hierarchical neural characterization of speech processing |
| US20190117106A1 (en) * | 2016-04-18 | 2019-04-25 | Cerora, Inc. | Protocol and signatures for the multimodal physiological stimulation and assessment of traumatic brain injury |
| CN106502386B (en) * | 2016-09-26 | 2018-07-31 | 苏州大学 | Method for establishing non-attention event related potential brain-computer interface for automatic color vision identification |
-
2021
- 2021-04-25 CN CN202110448301.0A patent/CN113040787B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512500A (en) * | 2015-12-30 | 2016-04-20 | 广州市润杰医疗器械有限公司 | Method for rapidly screening characteristic of schizophrenia and evaluating therapeutic effect |
| CN110063732A (en) * | 2019-04-15 | 2019-07-30 | 北京航空航天大学 | For schizophrenia early detection and Risk Forecast System |
| CN111248907A (en) * | 2020-01-17 | 2020-06-09 | 上海市精神卫生中心（上海市心理咨询培训中心） | Risk prediction method based on electroencephalogram signal characteristics of mental disease clinical high-risk group |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113040787A (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Debnath et al. | The Maryland analysis of developmental EEG (MADE) pipeline | |
| US8340752B2 (en) | Method, apparatus and computer program product for assessment of attentional impairments | |
| Karthikeyan et al. | Detection of human stress using short-term ECG and HRV signals | |
| Albert et al. | Automatic EEG processing for the early diagnosis of traumatic brain injury | |
| US20150245800A1 (en) | Method for Detection Of An Abnormal Sleep Pattern In A Person | |
| AU2002305384A1 (en) | Method, apparatus, and computer program product for assessment of attentional impairments | |
| EP1880667A2 (en) | Detection of focal epileptiform activity | |
| Tan | Using a low-cost eeg sensor to detect mental states | |
| Ren et al. | Redaction of false high frequency oscillations due to muscle artifact improves specificity to epileptic tissue | |
| CN113040787B (en) | Method, device, processor and storage medium for extracting and processing MMN signal characteristics for evaluating sensory gating function | |
| Joshi et al. | Spatiotemporal analysis of interictal EEG for automated seizure detection and classification | |
| Shaik Gadda et al. | Optimization of pre-ictal interval time period for epileptic seizure prediction using temporal and frequency features | |
| Thomschewski et al. | Automatic vs. manual detection of high frequency oscillations in intracranial recordings from the human temporal lobe | |
| Gholamipour et al. | Estimation of the independent components reliability of EEG signal in a clinical application | |
| KR20230173439A (en) | Methods for predicting delirium occurrence and devices using the same | |
| Al-Bakri et al. | Effect of Vigilance Changes on the Incidence of High Frequency Oscillations in the Epileptic Brain | |
| Liang et al. | Detection of myasthenia gravis using electrooculography signals | |
| Rosado et al. | Automatic detection of epileptiform discharges in the eeg | |
| TH et al. | Improved feature exctraction process to detect seizure using CHBMIT-dataset | |
| Jyothirmy et al. | Stress Monitoring in Humans using Biomedical Signal Analysis | |
| Yazdanpour-Naeini | Automatic detection of high frequency oscillations of neural signals in epileptic patients | |
| Greene et al. | Automated single channel seizure detection in the neonate | |
| Rajalakshmi et al. | Electroencephalogram data analysed through the lens of machine learning to detect signs of epilepsy | |
| Boashash et al. | On-line detection of seizure in newborn EEG using signal processing tools | |
| US20240423528A1 (en) | Brain activity detection device and brain activity detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |